Skip to content

Platform

Status

Live in production. A fleet of AI devs, code review, and self-hosted CI running today — on your hardware, on your keys, every action audited and disclosed.

Fleet / live3 active
Agent 01

Upgrade zod across services

  • Read repository context
  • Proposed implementation plan
  • Running checks
Agent 02

Fix auth redirect loop

  • Read repository context
  • Proposed implementation plan
  • Writing tests
Agent 03

Refresh the quickstart

  • Read repository context
  • Proposed implementation plan
  • Opening pull request
Audited end to endGitHub-native workflowExisting checks stay in controlCost visible per task

Live in production today

The maintainer agent

Triage, hand-off to your coding agent, PR shepherding and releases run in production today, on your keys and your boxes.

AI code review

The review lane is live, reads an existing .coderabbit.yaml, and posts under the same App as everything else.

Self-hosted CI runners

Your VMs act as just-in-time GitHub Actions runners. Three runners are included with each AI dev.

Where to look

  • Changelog

    Every shipped change, dated. This is the fastest way to see whether something moved recently.

  • Documentation

    How each surface is meant to behave — the reference to check a suspicion against before reporting.

  • OSS directory

    Public repositories the agent maintains, with the work it handled. Real activity, not a green dot.

  • Report an incident

    Something broken or behaving oddly? Tell us directly. A cached status page would not have told you anyway.

Put a fleet of AI developers to work

Bring your own keys and your own boxes, drop a .maintainer.yml, and let the loops run — audited end to end. Access is invite-only.